OmniXAS: A universal deep-learning framework for materials x-ray absorption spectra
Source abstract
Abstract
X-ray absorption spectroscopy (XAS) is a powerful technique for probing local chemical environments. However, interpreting XAS spectra remains challenging, due to high computational costs and the need for domain expertise. To overcome these barriers, we introduce OmniXAS, a graph neural network framework that leverages transfer learning to directly predict XAS spectra from atomic structures. By capturing the shared spectral trends across the 3d transition metal family, OmniXAS learns a universal model that can be effectively fine-tuned on each specific element. OmniXAS achieves high predictive accuracy as demonstrated on the K-edge spectra of eight 3d transition metals (Ti--Cu), enabling real-time prediction of XAS spectra with minimal computational overhead.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Advanced X-ray and CT Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Brookhaven National Laboratory
Center for Functional Nanomaterials, Brookhaven National Laboratory
Funding
U.S. Department of Energy · Office of Science · Basic Energy Sciences · Brookhaven National Laboratory · Laboratory Directed Research and Development · National Energy Research Scientific Computing Center · Lawrence Berkeley National Laboratory
References (64)
Show source-provided references
1. 10.1103/RevModPhys.72.62110.1103/RevModPhys.72.621 ↗
2. 10.1016/S0010-8545(99)00160-510.1016/S0010-8545(99)00160-5 ↗
3. F. De Groot · 2008
4. 10.1103/PhysRevB.56.180910.1103/PhysRevB.56.1809 ↗
5. 10.1107/S160057751501800710.1107/S1600577515018007 ↗
6. 10.1103/PhysRevB.66.19511210.1103/PhysRevB.66.195112 ↗
7. 10.1088/1361-6528/acd25a10.1088/1361-6528/acd25a ↗
8. 10.1016/j.matt.2023.11.01210.1016/j.matt.2023.11.012 ↗
9. 10.1103/PhysRevMaterials.8.01380110.1103/PhysRevMaterials.8.013801 ↗
10. 10.1088/1742-6596/430/1/01200710.1088/1742-6596/430/1/012007 ↗
11. 10.1107/S160057752100861410.1107/S1600577521008614 ↗
12. 10.21105/joss.0518210.21105/joss.05182 ↗
13. 10.1038/sdata.2018.15110.1038/sdata.2018.151 ↗
14. 10.1038/s41524-020-00376-610.1038/s41524-020-00376-6 ↗
15. 10.1038/s41597-021-00936-510.1038/s41597-021-00936-5 ↗
16. 10.1038/s41524-021-00664-910.1038/s41524-021-00664-9 ↗
17. 10.1063/5.008725510.1063/5.0087255 ↗
18. 10.1038/s41597-023-02262-410.1038/s41597-023-02262-4 ↗
19. 10.1016/j.xcrp.2024.10190910.1016/j.xcrp.2024.101909 ↗
20. 10.1103/PhysRevLett.98.14640110.1103/PhysRevLett.98.146401 ↗
21. 10.1103/PhysRevLett.124.15640110.1103/PhysRevLett.124.156401 ↗
22. 10.1103/PhysRevResearch.5.01318010.1103/PhysRevResearch.5.013180 ↗
23. 10.1038/sdata.2014.2210.1038/sdata.2014.22 ↗
24. 10.1021/acs.jpcc.3c0202910.1021/acs.jpcc.3c02029 ↗
25. 10.1021/acs.jpca.0c0372310.1021/acs.jpca.0c03723 ↗
26. 10.1088/2632-2153/ad8c1010.1088/2632-2153/ad8c10 ↗
27. 10.1038/s43588-022-00349-310.1038/s43588-022-00349-3 ↗
28. 10.1039/b926434e10.1039/b926434e ↗
29. 10.1103/PhysRevB.98.23520510.1103/PhysRevB.98.235205 ↗
30. 10.1016/j.commatsci.2012.10.02810.1016/j.commatsci.2012.10.028 ↗
31. 10.1109/MCSE.2011.3710.1109/MCSE.2011.37 ↗
32. 10.1016/j.cplett.2011.08.06310.1016/j.cplett.2011.08.063 ↗
33. 10.1021/jp511739h10.1021/jp511739h ↗
34. 10.1088/1742-6596/190/1/01208410.1088/1742-6596/190/1/012084 ↗
35. L. Torrey · 2010
36. 10.1109/JPROC.2020.300455510.1109/JPROC.2020.3004555 ↗
37. B. Kulis · 2011
38. Y. Zhu · 2011
39. J. Zhou · 2014
40. P. Prettenhofer · 2010
41. J. T. Zhou · 2014
42. R. Xia · 2011
43. 10.1109/TKDE.2009.19110.1109/TKDE.2009.191 ↗
44. 10.1007/BF0133263910.1007/BF01332639 ↗
45. 10.1135/cccc1932021310.1135/cccc19320213 ↗
46. L. Pauling · 1960
47. J. P. Suchet · 1965
48. 10.1002/xrs.110310.1002/xrs.1103 ↗
49. 10.1103/PhysRevMaterials.3.03360410.1103/PhysRevMaterials.3.033604 ↗
50. 10.1103/PhysRevMaterials.7.05380210.1103/PhysRevMaterials.7.053802 ↗
51. J. Krause · 2016
52. 10.1038/538020a10.1038/538020a ↗
53. S. Ioffe · 2015
54. T. Akiba
55. J. Bergstra · Adv. Neural Inf. Proc. Syst. · 2011 · 24
56. D. Chen · 2020
57. 10.1016/j.cpc.2019.10694910.1016/j.cpc.2019.106949 ↗
58. 10.1039/C6CP00415F10.1039/C6CP00415F ↗
59. 10.1063/1.355371710.1063/1.3553717 ↗
60. 10.1103/PhysRevB.87.18411510.1103/PhysRevB.87.184115 ↗
61. 10.1371/journal.pone.009376610.1371/journal.pone.0093766 ↗
62. 10.1073/pnas.231187812110.1073/pnas.2311878121 ↗
63. 10.1038/s41597-020-00637-510.1038/s41597-020-00637-5 ↗
64. 10.24435/materialscloud:85-8x10.24435/materialscloud:85-8x ↗